Exploring wavefield-based location imaging in heterogeneous media: A borehole DAS example

Abstract Earthquake localization using distributed acoustic sensing (DAS) is challenging due to the single-component direc tional sensitivity of DAS systems. A novel approach for localization was proposed, based on dense DAS recordings and constraints from known structural heterogeneity of the subsurface. Our method uses full-waveform simulations to generate synthetic DAS wavefield images for a range of potential earthquake source locations. A deep convolutional neural network (CNN), based on a U-Net architecture, is trained on these images to map DAS-recorded wavefield patterns to earthquake source coordinates, without the need for identification and picking of P- and S-wave arrivals. This wavefield-based localization technique was evaluated based on a challenging synthetic case study involving DAS recordings in a single vertical borehole only. Different velocity models of varying geologic complexity were considered. The results show that the CNN effectively learns location-specific wavefield signatures influenced by subsurface heterogeneity. Uncertain ties can be reduced significantly by adding recordings from a second borehole. Although the results are based on idealized 2D synthetic modeling, the method offers a promising approach for improving microseismic monitoring when detailed information on the heterogeneous velocity structure is available (such as that derived from seismic surveys).